Rates of Convergence for Nearest Neighbor Classification

Authors: Kamalika Chaudhuri, Sanjoy Dasgupta

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We analyze the behavior of nearest neighbor classification in metric spaces and provide finite-sample, distribution-dependent rates of convergence under minimal assumptions. We illustrate our upper and lower bounds by introducing a new smoothness class customized for nearest neighbor classification.
Researcher Affiliation Academia Kamalika Chaudhuri Computer Science and Engineering University of California, San Diego kamalika@cs.ucsd.edu Sanjoy Dasgupta Computer Science and Engineering University of California, San Diego dasgupta@cs.ucsd.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., specific repository link, explicit code release statement) for source code.
Open Datasets No The paper is theoretical and does not mention using any specific datasets, thus no information on public availability.
Dataset Splits No The paper is theoretical and does not describe any specific dataset split information (e.g., train/validation/test percentages or counts).
Hardware Specification No The paper is theoretical and does not provide any specific hardware details used for running experiments.
Software Dependencies No The paper is theoretical and does not provide any specific ancillary software details with version numbers.
Experiment Setup No The paper is theoretical and does not describe any specific experimental setup details like hyperparameter values or training configurations.